Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0311. Min Act: -0.0006

Data Index: 587354 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0006

Data Index: 990230 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0307. Min Act: -0.0006

Data Index: 265611 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0313. Min Act: -0.0006

Data Index: 961997 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0293. Min Act: -0.0006

Data Index: 466356 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0006

Data Index: 774177 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1058572 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0304. Min Act: -0.0006

Data Index: 570157 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0310. Min Act: -0.0006

Data Index: 431362 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0283. Min Act: -0.0006

Data Index: 933642 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0294. Min Act: -0.0006

Data Index: 111640 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1299828 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1135846 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0304. Min Act: -0.0006

Data Index: 65898 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0288. Min Act: -0.0006

Data Index: 423872 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1116763 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0308. Min Act: -0.0006

Data Index: 715202 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1188697 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0279. Min Act: -0.0006

Data Index: 6678 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0282. Min Act: -0.0006

Data Index: 27596 (C4 (Web Text))

Max Activating Token Index: 45